© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42777
    Prev
    Next
    INDEX
    Explanations

    banana

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apa
    -0.95
     bananas
    -0.91
     itſelf
    -0.90
    NewUrlParser
    -0.89
     apa
    -0.86
    ſelves
    -0.84
    ſelf
    -0.84
     myſelf
    -0.82
     iſt
    -0.81
     ―――――
    -0.79
    POSITIVE LOGITS
     sea
    0.52
    i
    0.52
     t
    0.47
     (
    0.47
    a
    0.46
    chii
    0.46
     Da
    0.46
     w
    0.45
     Trouble
    0.45
    vų
    0.45
    Activations Density 0.277%

    No Known Activations